Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An extensive evaluation and comparison of 28 state-of-the-art superpixel algorithms on 5 datasets.
| Date | Stars |
|---|---|
| 2026-07-24 | 415 |
| 2026-07-25 | 415 |
| 2026-07-28 | 415 |
| 2026-07-30 | 415 |
| 2026-08-06 | 415 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Superpixels: An Evaluation of the State-of-the-Art
[](https://travis-ci.org/davidstutz/superpixel-benchmark)
This repository contains the source code used for evaluation in [1], a large-scale
comparison of state-of-the-art superpixel algorithms.
**[ArXiv](https://arxiv.org/abs/1612.01601) |
[Project Page](http://davidstutz.de/projects/superpixel-benchmark/) |
[Datasets](https://github.com/davidstutz/superpixel-benchmark-data) |
[Doxygen Documentation](https://davidstutz.github.io/superpixel-benchmark/)**
This repository subsumes earlier work on comparing superpixel algorithms:
[davidstutz/gcpr2015-superpixels](https://github.com/davidstutz/gcpr2015-superpixels),
[davidstutz/superpixels-revisited](https://github.com/davidstutz/superpixels-revisited).
**Please cite the following work if you use this benchmark or the provided tools or implementations:**
[1] D. Stutz, A. Hermans, B. Leibe.
Superpixels: An Evaluation of the State-of-the-Art.
Computer Vision and Image Understanding, 2018.
Also make also sure to cite additional papers when using datasets or superpixel algorithms.
**Updates:**
* The docker files have been updated to the latest debian releases as well as ARM64 in [PR18](https://github.com/davidstutz/superpixel-benchmark/pull/18).
* A docker implementation containing many of the algorithms was added to [./docker](./docker/).
* An implementation of the average metrics, i.e. Average Boundary Recall (called
Average Miss Rate in the updated paper), Average Undersegmentation Error
and Average Explained Variation (called Average Unexplained Variation in the updated paper)
is provided in `lib_eval/evaluation.h` and an easy-to-use command line tool is provided,
see `eval_average_cli` and the corresponding documentation and examples in
[Executables](docs/EXECUTABLES.md) and [Examples](docs/EXAMPLE.md) respectively.
* As of Mar 29, 2017 the paper was accepted for publication at
[CVIU](https://www.journals.elsevier.com/computer-vision-and-image-understanding/).
* The converted (i.e. pre-processed) NYUV2, SBD and SUNRGBD datasets are now available
in the [data repository](https://github.com/davidstutz/superpixel-benchmark-data).
* The source code of MSS has been added.
* The source code of PF and SEAW has been added.
* Doxygen documentation is now available [here](http://davidstutz.github.io/superpixel-benchmark/).
* The presented paper was in preparation for a longer period of time —
some recent superpixel algorithms are not included in the comparison. These include
[SCSP](https://github.com/freifeld/fastSCSP) and [LRW](https://github.com/shenjianbing/lrw14).
## Table of Contents
* [Introduction](#introduction)
* [Algorithms](#algorithms)
* [Submission](#submission)
* [Documentation](docs/README.md)
* [Datasets](docs/DATASETS.md)
* [Algorithms](docs/ALGORITHMS.md)
* [Submission](docs/SUBMISSION.md)
* [Benchmark](docs/BENCHMARK.md)
* [Building](docs/BUILDING.md)
* [Building CIS](docs/BUILDING_CIS.md)
* [Executables](docs/EXECUTABLES.md)
* [Examples](docs/EXAMPLES.md)
* [Parameters](docs/PARAMETERS.md)
* [Results](docs/RESULTS.md)
* [Data](docs/DATA.md)
* [License](#license)
## Introduction
Superpixels group pixels similar in color and other low-level properties.
In this respect, superpixels address two problems inherent to the processing of
digital images: firstly, pixels are merely a result of discretization;
and secondly, the high number of pixels in large images prevents many algorithms
from being computationally feasible. Superpixels were introduced as more natural
entities - grouping pixels which perceptually belong together while heavily reducing
the number of primitives.
This repository can be understood as supplementary material for an extensive
evaluation of 28 algorithms on 5 datasets regarding visual quality, performance,
ruExcerpt of 13,393 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1d9bc5b714daeeaf, topic:computer-vision, topic:opencv, readme:computer vision
matched fp:1d9bc5b714daeeaf, topic:benchmark, topic:evaluation